Instructions to use keras-io/ocr-for-captcha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use keras-io/ocr-for-captcha with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy), and from_pretrained_keras was removed in huggingface_hub 1.0. # See https://github.com/keras-team/tf-keras for more details. # !pip install "huggingface_hub<1.0" tf_keras from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("keras-io/ocr-for-captcha") - Notebooks
- Google Colab
- Kaggle
Tricky images
#3
by 10basetom - opened
This is a good start, but there's room for improvement. For example, I tested with the first image here, but it failed:
https://captcha.com/captcha-examples.html
Expected result for first image: W93BX
Got this result instead: x7[UNK][UNK][UNK]
The ultimate goal would be to be able to correctly read the text from all of the images on this page with 100% accuracy.